INDEX

Explanations

instances of the word "drone" and related terms

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orie

-1.11

rosso

-1.09

orio

-1.07

Pep

-1.02

 Cumber

-1.00

 Camb

-0.95

urgy

-0.92

opath

-0.92

 Doyle

-0.92

oire

-0.92

POSITIVE LOGITS

 drone

1.41

 drones

1.33

 buzzing

1.07

istani

1.04

iverse

1.04

 pilots

1.02

 strike

1.02

Deploy

1.00

 swarm

0.99

 Drone

0.98

Activations Density 0.787%

instances of the word "drone" and related terms

No Comments

No Known Activations